Interesting article from Alphr on how MIT is using driverless technology for drone search and rescue:
The process of search and rescue over thickly wooded areas has remained a difficult task for humans. From the sky it’s nearly impossible to see through the treetops; from the ground, GPS signals aren’t completely reliable and the operational demand on humans is great. Recently the use of autonomous drones has been discussed, however until now the issue of GPS signal has befallen them, too. What’s more, current drone programming limitations means distinguishing trees from one another is troublesome – to a drone, all trees are similarly circular, and this gives them a headache.
MIT researchers have developed a solution, though. By using the same laser systems found in driverless cars, the drones move around scanning the area before them, allowing them to create a 3D map of the vicinity they’re searching. The research team then created a new algorithm for the drones, allowing them to view the spatial data they’ve retrieved in terms of recognisable patterns. Individually, trees are tricky characters for the drones to understand, but a single cluster of trees will project a pattern different to another cluster, and the algorithm allows the drone to interpret this and gain a bearing from it.
Welcome to drone day on the Adafruit blog. Every Monday we deliver the latest news, products and more from the Unmanned Aerial Vehicles (UAV), quadcopter and drone communities. Drones can be used for video & photography (dronies), civil applications, policing, farming, firefighting, military and non-military security work, such as surveillance of pipelines. Previous posts can be found via the #drone tag and our drone / UAV categories.